Method and apparatus for detecting incorrectly translated text in a document

Abstract

A system that detects incorrectly translated text in a document. During operation, the system determines a target language for the document. The system then identifies one or more terms in the document that are invalid terms for the language. Next, the system analyzes correlations between these invalid terms, and, based on these correlations, determines whether one or more of the invalid terms comprise incorrectly translated text.

Description

BACKGROUND[0001]1. Field[0002]The described embodiments relate to techniques for detecting incorrectly translated and / or untranslated text in a document.[0003]2. Related Art[0004]Easy access to computers and plentiful network bandwidth have made it very easy to distribute computer-based applications globally. In order to distribute an application globally, the application may need to be translated into multiple languages to accommodate different locales. This translation process often involves dividing the text associated with the application into specific units, translating these units individually into one or more languages, and then recombining the translated units to form a translated application. Unfortunately, this translation process involves many steps, each of which can potentially introduce errors into the final result.[0005]Quality assurance engineers typically manually verify that a final translated application seen by customers has been translated properly for all of th...

AI Technical Summary

Benefits of technology

[0014]In some embodiments, the system uses a web-crawler to determine one or more documents associated with an application. The system then identifies any incorrectly translated text in these documents. Note that such documents may include static documents as well as documents that are dynamically created by the application at run-time.

Problems solved by technology

Unfortunately, this translation process involves many steps, each of which can potentially introduce errors into the final result.

However, manually reading and testing each page of an application to find translation errors becomes unscalable as the number of applications and languages grows.

For instance, translating an application into forty different languages may require a significant amount of time, with each application page and / or change requiring forty different tests.

Furthermore, obtaining the personnel to verify the correctness of the translated end results and correctly identify errors in forty languages may be difficult in practice.

Images